From 53e4d6eedb0e515b8fd7351c1475ebc7c1a5a48b Mon Sep 17 00:00:00 2001 From: Francisco Casas Date: Mon, 4 Mar 2024 18:56:23 -0300 Subject: [PATCH] vkd3d-shader/hlsl: Use LOGIC_OR instead of BIT_OR in any(). Note that BIT_OR is not available for SM1 bools, so we must prefer LOGIC_OR when possible. --- libs/vkd3d-shader/hlsl.y | 90 +++++++++++++++++--------------------- tests/hlsl/any.shader_test | 20 ++++----- 2 files changed, 49 insertions(+), 61 deletions(-) diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index 1f65df2a..11e504ac 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -2728,6 +2728,38 @@ static bool intrinsic_acos(struct hlsl_ctx *ctx, return write_acos_or_asin(ctx, params, loc, false); } +/* Find the type corresponding to the given source type, with the same + * dimensions but a different base type. */ +static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, + const struct hlsl_type *type, enum hlsl_base_type base_type) +{ + return hlsl_get_numeric_type(ctx, type->class, base_type, type->dimx, type->dimy); +} + +static bool add_combine_components(struct hlsl_ctx *ctx, const struct parse_initializer *params, + struct hlsl_ir_node *arg, enum hlsl_ir_expr_op op, const struct vkd3d_shader_location *loc) +{ + struct hlsl_ir_node *res, *load; + unsigned int i, count; + + count = hlsl_type_component_count(arg->data_type); + + if (!(res = hlsl_add_load_component(ctx, params->instrs, arg, 0, loc))) + return false; + + for (i = 1; i < count; ++i) + { + if (!(load = hlsl_add_load_component(ctx, params->instrs, arg, i, loc))) + return false; + + if (!(res = hlsl_new_binary_expr(ctx, op, res, load))) + return NULL; + hlsl_block_add_instr(params->instrs, res); + } + + return true; +} + static bool intrinsic_all(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { @@ -2757,52 +2789,17 @@ static bool intrinsic_all(struct hlsl_ctx *ctx, return !!add_binary_comparison_expr(ctx, params->instrs, HLSL_OP2_NEQUAL, mul, zero, loc); } -static bool intrinsic_any(struct hlsl_ctx *ctx, - const struct parse_initializer *params, const struct vkd3d_shader_location *loc) +static bool intrinsic_any(struct hlsl_ctx *ctx, const struct parse_initializer *params, + const struct vkd3d_shader_location *loc) { - struct hlsl_ir_node *arg = params->args[0], *dot, *or, *zero, *bfalse, *load; - unsigned int i, count; + struct hlsl_ir_node *arg = params->args[0], *cast; + struct hlsl_type *bool_type; - if (arg->data_type->class != HLSL_CLASS_VECTOR && arg->data_type->class != HLSL_CLASS_SCALAR) - { - hlsl_fixme(ctx, loc, "any() implementation for non-vector, non-scalar"); + bool_type = convert_numeric_type(ctx, arg->data_type, HLSL_TYPE_BOOL); + if (!(cast = add_cast(ctx, params->instrs, arg, bool_type, loc))) return false; - } - if (arg->data_type->base_type == HLSL_TYPE_FLOAT) - { - if (!(zero = hlsl_new_float_constant(ctx, 0.0f, loc))) - return false; - hlsl_block_add_instr(params->instrs, zero); - - if (!(dot = add_binary_dot_expr(ctx, params->instrs, arg, arg, loc))) - return false; - - return !!add_binary_comparison_expr(ctx, params->instrs, HLSL_OP2_NEQUAL, dot, zero, loc); - } - else if (arg->data_type->base_type == HLSL_TYPE_BOOL) - { - if (!(bfalse = hlsl_new_bool_constant(ctx, false, loc))) - return false; - hlsl_block_add_instr(params->instrs, bfalse); - - or = bfalse; - - count = hlsl_type_component_count(arg->data_type); - for (i = 0; i < count; ++i) - { - if (!(load = hlsl_add_load_component(ctx, params->instrs, arg, i, loc))) - return false; - - if (!(or = add_binary_bitwise_expr(ctx, params->instrs, HLSL_OP2_BIT_OR, or, load, loc))) - return false; - } - - return true; - } - - hlsl_fixme(ctx, loc, "any() implementation for non-float, non-bool"); - return false; + return add_combine_components(ctx, params, cast, HLSL_OP2_LOGIC_OR, loc); } static bool intrinsic_asin(struct hlsl_ctx *ctx, @@ -2903,15 +2900,6 @@ static bool intrinsic_atan2(struct hlsl_ctx *ctx, return write_atan_or_atan2(ctx, params, loc, true); } - -/* Find the type corresponding to the given source type, with the same - * dimensions but a different base type. */ -static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, - const struct hlsl_type *type, enum hlsl_base_type base_type) -{ - return hlsl_get_numeric_type(ctx, type->class, base_type, type->dimx, type->dimy); -} - static bool intrinsic_asfloat(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { diff --git a/tests/hlsl/any.shader_test b/tests/hlsl/any.shader_test index b143dd41..8a740828 100644 --- a/tests/hlsl/any.shader_test +++ b/tests/hlsl/any.shader_test @@ -49,7 +49,7 @@ todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) -[pixel shader todo(sm<4)] +[pixel shader] uniform uint4 b; float4 main() : sv_target @@ -60,30 +60,30 @@ float4 main() : sv_target [test] if(sm<4) uniform 0 float4 1 1 1 1 if(sm>=4) uniform 0 uint4 1 1 1 1 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 1 0 0 0 if(sm>=4) uniform 0 uint4 1 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 1 0 0 if(sm>=4) uniform 0 uint4 0 1 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 1 0 if(sm>=4) uniform 0 uint4 0 0 1 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 1 if(sm>=4) uniform 0 uint4 0 0 0 1 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 0 if(sm>=4) uniform 0 uint4 0 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0) -[pixel shader todo(sm<4)] +[pixel shader] uniform uint b; float4 main() : sv_target @@ -94,9 +94,9 @@ float4 main() : sv_target [test] if(sm<4) uniform 0 float4 1 0 0 0 if(sm>=4) uniform 0 uint4 1 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (1.0, 1.0, 1.0, 1.0) if(sm<4) uniform 0 float4 0 0 0 0 if(sm>=4) uniform 0 uint4 0 0 0 0 -todo(sm<4 | glsl) draw quad +todo(glsl) draw quad probe all rgba (0.0, 0.0, 0.0, 0.0)